Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    taken names or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ана
    0.39
    しば
    0.38
    boo
    0.37
     ไง
    0.36
     sectoral
    0.36
    OneFrame
    0.36
    Apakah
    0.35
    ар
    0.35
     inclined
    0.35
     одного
    0.35
    POSITIVE LOGITS
     తగ్గ
    0.52
     Capacity
    0.47
     Deaths
    0.45
     reik
    0.43
     Backup
    0.43
     Traits
    0.43
     Companies
    0.42
    睃
    0.41
    Deaths
    0.41
     Accountants
    0.40
    Act Density 0.000%

    No Known Activations